Training in progress, step 300, checkpoint
Browse files- last-checkpoint/README.md +210 -0
- last-checkpoint/adapter_config.json +50 -0
- last-checkpoint/adapter_model.safetensors +3 -0
- last-checkpoint/chat_template.jinja +1 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +13 -0
- last-checkpoint/trainer_state.json +2134 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/README.md
ADDED
|
@@ -0,0 +1,210 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: unsloth/phi-4-reasoning-unsloth-bnb-4bit
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:unsloth/phi-4-reasoning-unsloth-bnb-4bit
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
- unsloth
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Model Card for Model ID
|
| 15 |
+
|
| 16 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
## Model Details
|
| 21 |
+
|
| 22 |
+
### Model Description
|
| 23 |
+
|
| 24 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
- **Developed by:** [More Information Needed]
|
| 29 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 30 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 31 |
+
- **Model type:** [More Information Needed]
|
| 32 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 33 |
+
- **License:** [More Information Needed]
|
| 34 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
### Model Sources [optional]
|
| 37 |
+
|
| 38 |
+
<!-- Provide the basic links for the model. -->
|
| 39 |
+
|
| 40 |
+
- **Repository:** [More Information Needed]
|
| 41 |
+
- **Paper [optional]:** [More Information Needed]
|
| 42 |
+
- **Demo [optional]:** [More Information Needed]
|
| 43 |
+
|
| 44 |
+
## Uses
|
| 45 |
+
|
| 46 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 47 |
+
|
| 48 |
+
### Direct Use
|
| 49 |
+
|
| 50 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 51 |
+
|
| 52 |
+
[More Information Needed]
|
| 53 |
+
|
| 54 |
+
### Downstream Use [optional]
|
| 55 |
+
|
| 56 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 57 |
+
|
| 58 |
+
[More Information Needed]
|
| 59 |
+
|
| 60 |
+
### Out-of-Scope Use
|
| 61 |
+
|
| 62 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 63 |
+
|
| 64 |
+
[More Information Needed]
|
| 65 |
+
|
| 66 |
+
## Bias, Risks, and Limitations
|
| 67 |
+
|
| 68 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 69 |
+
|
| 70 |
+
[More Information Needed]
|
| 71 |
+
|
| 72 |
+
### Recommendations
|
| 73 |
+
|
| 74 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 75 |
+
|
| 76 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 77 |
+
|
| 78 |
+
## How to Get Started with the Model
|
| 79 |
+
|
| 80 |
+
Use the code below to get started with the model.
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
## Training Details
|
| 85 |
+
|
| 86 |
+
### Training Data
|
| 87 |
+
|
| 88 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
### Training Procedure
|
| 93 |
+
|
| 94 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 95 |
+
|
| 96 |
+
#### Preprocessing [optional]
|
| 97 |
+
|
| 98 |
+
[More Information Needed]
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
#### Training Hyperparameters
|
| 102 |
+
|
| 103 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 104 |
+
|
| 105 |
+
#### Speeds, Sizes, Times [optional]
|
| 106 |
+
|
| 107 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 108 |
+
|
| 109 |
+
[More Information Needed]
|
| 110 |
+
|
| 111 |
+
## Evaluation
|
| 112 |
+
|
| 113 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 114 |
+
|
| 115 |
+
### Testing Data, Factors & Metrics
|
| 116 |
+
|
| 117 |
+
#### Testing Data
|
| 118 |
+
|
| 119 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 120 |
+
|
| 121 |
+
[More Information Needed]
|
| 122 |
+
|
| 123 |
+
#### Factors
|
| 124 |
+
|
| 125 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 126 |
+
|
| 127 |
+
[More Information Needed]
|
| 128 |
+
|
| 129 |
+
#### Metrics
|
| 130 |
+
|
| 131 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 132 |
+
|
| 133 |
+
[More Information Needed]
|
| 134 |
+
|
| 135 |
+
### Results
|
| 136 |
+
|
| 137 |
+
[More Information Needed]
|
| 138 |
+
|
| 139 |
+
#### Summary
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
|
| 143 |
+
## Model Examination [optional]
|
| 144 |
+
|
| 145 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 146 |
+
|
| 147 |
+
[More Information Needed]
|
| 148 |
+
|
| 149 |
+
## Environmental Impact
|
| 150 |
+
|
| 151 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 152 |
+
|
| 153 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 154 |
+
|
| 155 |
+
- **Hardware Type:** [More Information Needed]
|
| 156 |
+
- **Hours used:** [More Information Needed]
|
| 157 |
+
- **Cloud Provider:** [More Information Needed]
|
| 158 |
+
- **Compute Region:** [More Information Needed]
|
| 159 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 160 |
+
|
| 161 |
+
## Technical Specifications [optional]
|
| 162 |
+
|
| 163 |
+
### Model Architecture and Objective
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
### Compute Infrastructure
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
#### Hardware
|
| 172 |
+
|
| 173 |
+
[More Information Needed]
|
| 174 |
+
|
| 175 |
+
#### Software
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
## Citation [optional]
|
| 180 |
+
|
| 181 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 182 |
+
|
| 183 |
+
**BibTeX:**
|
| 184 |
+
|
| 185 |
+
[More Information Needed]
|
| 186 |
+
|
| 187 |
+
**APA:**
|
| 188 |
+
|
| 189 |
+
[More Information Needed]
|
| 190 |
+
|
| 191 |
+
## Glossary [optional]
|
| 192 |
+
|
| 193 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## More Information [optional]
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
## Model Card Authors [optional]
|
| 202 |
+
|
| 203 |
+
[More Information Needed]
|
| 204 |
+
|
| 205 |
+
## Model Card Contact
|
| 206 |
+
|
| 207 |
+
[More Information Needed]
|
| 208 |
+
### Framework versions
|
| 209 |
+
|
| 210 |
+
- PEFT 0.18.1
|
last-checkpoint/adapter_config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": {
|
| 6 |
+
"base_model_class": "Phi3ForCausalLM",
|
| 7 |
+
"parent_library": "transformers.models.phi3.modeling_phi3",
|
| 8 |
+
"unsloth_fixed": true
|
| 9 |
+
},
|
| 10 |
+
"base_model_name_or_path": "unsloth/phi-4-reasoning-unsloth-bnb-4bit",
|
| 11 |
+
"bias": "none",
|
| 12 |
+
"corda_config": null,
|
| 13 |
+
"ensure_weight_tying": false,
|
| 14 |
+
"eva_config": null,
|
| 15 |
+
"exclude_modules": null,
|
| 16 |
+
"fan_in_fan_out": false,
|
| 17 |
+
"inference_mode": true,
|
| 18 |
+
"init_lora_weights": true,
|
| 19 |
+
"layer_replication": null,
|
| 20 |
+
"layers_pattern": null,
|
| 21 |
+
"layers_to_transform": null,
|
| 22 |
+
"loftq_config": {},
|
| 23 |
+
"lora_alpha": 64,
|
| 24 |
+
"lora_bias": false,
|
| 25 |
+
"lora_dropout": 0.0,
|
| 26 |
+
"megatron_config": null,
|
| 27 |
+
"megatron_core": "megatron.core",
|
| 28 |
+
"modules_to_save": null,
|
| 29 |
+
"peft_type": "LORA",
|
| 30 |
+
"peft_version": "0.18.1",
|
| 31 |
+
"qalora_group_size": 16,
|
| 32 |
+
"r": 64,
|
| 33 |
+
"rank_pattern": {},
|
| 34 |
+
"revision": null,
|
| 35 |
+
"target_modules": [
|
| 36 |
+
"up_proj",
|
| 37 |
+
"o_proj",
|
| 38 |
+
"k_proj",
|
| 39 |
+
"down_proj",
|
| 40 |
+
"q_proj",
|
| 41 |
+
"v_proj",
|
| 42 |
+
"gate_proj"
|
| 43 |
+
],
|
| 44 |
+
"target_parameters": null,
|
| 45 |
+
"task_type": "CAUSAL_LM",
|
| 46 |
+
"trainable_token_indices": null,
|
| 47 |
+
"use_dora": false,
|
| 48 |
+
"use_qalora": false,
|
| 49 |
+
"use_rslora": false
|
| 50 |
+
}
|
last-checkpoint/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e974a9e9871067d6087b72108af8673328df742e190e49e5adeb5ba13851cbff
|
| 3 |
+
size 340808816
|
last-checkpoint/chat_template.jinja
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ad07eed758690626af66f0050d6785b86fe5e46f94e657c2b3ae425412418da
|
| 3 |
+
size 173247691
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
|
| 3 |
+
size 14645
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c59f6c0c3c7ac90729151078281ffd3574d86b4063a767b8e0ef9e412646652
|
| 3 |
+
size 1465
|
last-checkpoint/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|endoftext|>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"model_max_length": 32768,
|
| 9 |
+
"pad_token": "<|dummy_85|>",
|
| 10 |
+
"padding_side": "right",
|
| 11 |
+
"tokenizer_class": "TokenizersBackend",
|
| 12 |
+
"unk_token": "�"
|
| 13 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,2134 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.36809815950920244,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 300,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.001226993865030675,
|
| 14 |
+
"grad_norm": 0.056844476610422134,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.5532171726226807,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.00245398773006135,
|
| 21 |
+
"grad_norm": 0.05398453772068024,
|
| 22 |
+
"learning_rate": 7.668711656441719e-08,
|
| 23 |
+
"loss": 1.5773115158081055,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0036809815950920245,
|
| 28 |
+
"grad_norm": 0.06344727426767349,
|
| 29 |
+
"learning_rate": 1.5337423312883438e-07,
|
| 30 |
+
"loss": 1.3505765199661255,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0049079754601227,
|
| 35 |
+
"grad_norm": 0.06651192903518677,
|
| 36 |
+
"learning_rate": 2.3006134969325155e-07,
|
| 37 |
+
"loss": 1.4871529340744019,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.006134969325153374,
|
| 42 |
+
"grad_norm": 0.06967559456825256,
|
| 43 |
+
"learning_rate": 3.0674846625766876e-07,
|
| 44 |
+
"loss": 1.3247398138046265,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.007361963190184049,
|
| 49 |
+
"grad_norm": 0.05090988427400589,
|
| 50 |
+
"learning_rate": 3.834355828220859e-07,
|
| 51 |
+
"loss": 1.4368259906768799,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.008588957055214725,
|
| 56 |
+
"grad_norm": 0.05639501288533211,
|
| 57 |
+
"learning_rate": 4.601226993865031e-07,
|
| 58 |
+
"loss": 1.4667942523956299,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0098159509202454,
|
| 63 |
+
"grad_norm": 0.04931354150176048,
|
| 64 |
+
"learning_rate": 5.368098159509203e-07,
|
| 65 |
+
"loss": 1.4420663118362427,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.011042944785276074,
|
| 70 |
+
"grad_norm": 0.06962227076292038,
|
| 71 |
+
"learning_rate": 6.134969325153375e-07,
|
| 72 |
+
"loss": 1.3270829916000366,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.012269938650306749,
|
| 77 |
+
"grad_norm": 0.05681212246417999,
|
| 78 |
+
"learning_rate": 6.901840490797546e-07,
|
| 79 |
+
"loss": 1.3849859237670898,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.013496932515337423,
|
| 84 |
+
"grad_norm": 0.06245573237538338,
|
| 85 |
+
"learning_rate": 7.668711656441718e-07,
|
| 86 |
+
"loss": 1.390697956085205,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.014723926380368098,
|
| 91 |
+
"grad_norm": 0.051362067461013794,
|
| 92 |
+
"learning_rate": 8.43558282208589e-07,
|
| 93 |
+
"loss": 1.5184454917907715,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.015950920245398775,
|
| 98 |
+
"grad_norm": 0.057539232075214386,
|
| 99 |
+
"learning_rate": 9.202453987730062e-07,
|
| 100 |
+
"loss": 1.318811297416687,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.01717791411042945,
|
| 105 |
+
"grad_norm": 0.05592890456318855,
|
| 106 |
+
"learning_rate": 9.969325153374232e-07,
|
| 107 |
+
"loss": 1.2885284423828125,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.018404907975460124,
|
| 112 |
+
"grad_norm": 0.07110682129859924,
|
| 113 |
+
"learning_rate": 1.0736196319018406e-06,
|
| 114 |
+
"loss": 1.3424336910247803,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.0196319018404908,
|
| 119 |
+
"grad_norm": 0.05588489770889282,
|
| 120 |
+
"learning_rate": 1.1503067484662577e-06,
|
| 121 |
+
"loss": 1.4609296321868896,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.020858895705521473,
|
| 126 |
+
"grad_norm": 0.05414435639977455,
|
| 127 |
+
"learning_rate": 1.226993865030675e-06,
|
| 128 |
+
"loss": 1.346307635307312,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.022085889570552148,
|
| 133 |
+
"grad_norm": 0.05896000191569328,
|
| 134 |
+
"learning_rate": 1.303680981595092e-06,
|
| 135 |
+
"loss": 1.2913644313812256,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.023312883435582823,
|
| 140 |
+
"grad_norm": 0.05400668457150459,
|
| 141 |
+
"learning_rate": 1.3803680981595093e-06,
|
| 142 |
+
"loss": 1.3340139389038086,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.024539877300613498,
|
| 147 |
+
"grad_norm": 0.051172543317079544,
|
| 148 |
+
"learning_rate": 1.4570552147239264e-06,
|
| 149 |
+
"loss": 1.5014619827270508,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.025766871165644172,
|
| 154 |
+
"grad_norm": 0.06336528807878494,
|
| 155 |
+
"learning_rate": 1.5337423312883435e-06,
|
| 156 |
+
"loss": 1.4562170505523682,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.026993865030674847,
|
| 161 |
+
"grad_norm": 0.05446509271860123,
|
| 162 |
+
"learning_rate": 1.6104294478527609e-06,
|
| 163 |
+
"loss": 1.4978207349777222,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.02822085889570552,
|
| 168 |
+
"grad_norm": 0.053644318133592606,
|
| 169 |
+
"learning_rate": 1.687116564417178e-06,
|
| 170 |
+
"loss": 1.3169641494750977,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.029447852760736196,
|
| 175 |
+
"grad_norm": 0.059931203722953796,
|
| 176 |
+
"learning_rate": 1.763803680981595e-06,
|
| 177 |
+
"loss": 1.388343095779419,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.03067484662576687,
|
| 182 |
+
"grad_norm": 0.05717086419463158,
|
| 183 |
+
"learning_rate": 1.8404907975460124e-06,
|
| 184 |
+
"loss": 1.5201928615570068,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.03190184049079755,
|
| 189 |
+
"grad_norm": 0.07009559869766235,
|
| 190 |
+
"learning_rate": 1.9171779141104296e-06,
|
| 191 |
+
"loss": 1.4164372682571411,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.033128834355828224,
|
| 196 |
+
"grad_norm": 0.07497748732566833,
|
| 197 |
+
"learning_rate": 1.9938650306748465e-06,
|
| 198 |
+
"loss": 1.525839924812317,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.0343558282208589,
|
| 203 |
+
"grad_norm": 0.05568641796708107,
|
| 204 |
+
"learning_rate": 2.070552147239264e-06,
|
| 205 |
+
"loss": 1.2813575267791748,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.03558282208588957,
|
| 210 |
+
"grad_norm": 0.06756455451250076,
|
| 211 |
+
"learning_rate": 2.147239263803681e-06,
|
| 212 |
+
"loss": 1.4711202383041382,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.03680981595092025,
|
| 217 |
+
"grad_norm": 0.05878760293126106,
|
| 218 |
+
"learning_rate": 2.223926380368098e-06,
|
| 219 |
+
"loss": 1.436352252960205,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.03803680981595092,
|
| 224 |
+
"grad_norm": 0.06954875588417053,
|
| 225 |
+
"learning_rate": 2.3006134969325154e-06,
|
| 226 |
+
"loss": 1.5035226345062256,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.0392638036809816,
|
| 231 |
+
"grad_norm": 0.05211090296506882,
|
| 232 |
+
"learning_rate": 2.3773006134969327e-06,
|
| 233 |
+
"loss": 1.2772533893585205,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.04049079754601227,
|
| 238 |
+
"grad_norm": 0.05606016516685486,
|
| 239 |
+
"learning_rate": 2.45398773006135e-06,
|
| 240 |
+
"loss": 1.3446189165115356,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.04171779141104295,
|
| 245 |
+
"grad_norm": 0.06906063854694366,
|
| 246 |
+
"learning_rate": 2.530674846625767e-06,
|
| 247 |
+
"loss": 1.5665283203125,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.04294478527607362,
|
| 252 |
+
"grad_norm": 0.0749950110912323,
|
| 253 |
+
"learning_rate": 2.607361963190184e-06,
|
| 254 |
+
"loss": 1.3163764476776123,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.044171779141104296,
|
| 259 |
+
"grad_norm": 0.06453581154346466,
|
| 260 |
+
"learning_rate": 2.6840490797546016e-06,
|
| 261 |
+
"loss": 1.3515610694885254,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.04539877300613497,
|
| 266 |
+
"grad_norm": 0.06933236867189407,
|
| 267 |
+
"learning_rate": 2.7607361963190186e-06,
|
| 268 |
+
"loss": 1.391564130783081,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.046625766871165646,
|
| 273 |
+
"grad_norm": 0.06258511543273926,
|
| 274 |
+
"learning_rate": 2.8374233128834355e-06,
|
| 275 |
+
"loss": 1.3991773128509521,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.04785276073619632,
|
| 280 |
+
"grad_norm": 0.06230465695261955,
|
| 281 |
+
"learning_rate": 2.914110429447853e-06,
|
| 282 |
+
"loss": 1.4381181001663208,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.049079754601226995,
|
| 287 |
+
"grad_norm": 0.07217125594615936,
|
| 288 |
+
"learning_rate": 2.99079754601227e-06,
|
| 289 |
+
"loss": 1.676390290260315,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.05030674846625767,
|
| 294 |
+
"grad_norm": 0.07924707233905792,
|
| 295 |
+
"learning_rate": 3.067484662576687e-06,
|
| 296 |
+
"loss": 1.437603235244751,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.051533742331288344,
|
| 301 |
+
"grad_norm": 0.07502411305904388,
|
| 302 |
+
"learning_rate": 3.1441717791411044e-06,
|
| 303 |
+
"loss": 1.4542899131774902,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.05276073619631902,
|
| 308 |
+
"grad_norm": 0.08459946513175964,
|
| 309 |
+
"learning_rate": 3.2208588957055217e-06,
|
| 310 |
+
"loss": 1.5027896165847778,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.053987730061349694,
|
| 315 |
+
"grad_norm": 0.06554778665304184,
|
| 316 |
+
"learning_rate": 3.2975460122699386e-06,
|
| 317 |
+
"loss": 1.3057382106781006,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.05521472392638037,
|
| 322 |
+
"grad_norm": 0.06956043839454651,
|
| 323 |
+
"learning_rate": 3.374233128834356e-06,
|
| 324 |
+
"loss": 1.3026341199874878,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.05644171779141104,
|
| 329 |
+
"grad_norm": 0.09831614047288895,
|
| 330 |
+
"learning_rate": 3.4509202453987733e-06,
|
| 331 |
+
"loss": 1.357859492301941,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.05766871165644172,
|
| 336 |
+
"grad_norm": 0.09383076429367065,
|
| 337 |
+
"learning_rate": 3.52760736196319e-06,
|
| 338 |
+
"loss": 1.3813140392303467,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.05889570552147239,
|
| 343 |
+
"grad_norm": 0.07468827068805695,
|
| 344 |
+
"learning_rate": 3.6042944785276075e-06,
|
| 345 |
+
"loss": 1.5053529739379883,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.06012269938650307,
|
| 350 |
+
"grad_norm": 0.07278682291507721,
|
| 351 |
+
"learning_rate": 3.680981595092025e-06,
|
| 352 |
+
"loss": 1.3573490381240845,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.06134969325153374,
|
| 357 |
+
"grad_norm": 0.07713132351636887,
|
| 358 |
+
"learning_rate": 3.7576687116564418e-06,
|
| 359 |
+
"loss": 1.389432430267334,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.06257668711656442,
|
| 364 |
+
"grad_norm": 0.08927592635154724,
|
| 365 |
+
"learning_rate": 3.834355828220859e-06,
|
| 366 |
+
"loss": 1.354691982269287,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.0638036809815951,
|
| 371 |
+
"grad_norm": 0.07328439503908157,
|
| 372 |
+
"learning_rate": 3.911042944785277e-06,
|
| 373 |
+
"loss": 1.4615235328674316,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.06503067484662577,
|
| 378 |
+
"grad_norm": 0.1023353561758995,
|
| 379 |
+
"learning_rate": 3.987730061349693e-06,
|
| 380 |
+
"loss": 1.2745380401611328,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.06625766871165645,
|
| 385 |
+
"grad_norm": 0.09883410483598709,
|
| 386 |
+
"learning_rate": 4.064417177914111e-06,
|
| 387 |
+
"loss": 1.536147952079773,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.06748466257668712,
|
| 392 |
+
"grad_norm": 0.0988430604338646,
|
| 393 |
+
"learning_rate": 4.141104294478528e-06,
|
| 394 |
+
"loss": 1.233506679534912,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.0687116564417178,
|
| 399 |
+
"grad_norm": 0.09460455179214478,
|
| 400 |
+
"learning_rate": 4.2177914110429445e-06,
|
| 401 |
+
"loss": 1.4381420612335205,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.06993865030674846,
|
| 406 |
+
"grad_norm": 0.08306065201759338,
|
| 407 |
+
"learning_rate": 4.294478527607362e-06,
|
| 408 |
+
"loss": 1.373732328414917,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.07116564417177915,
|
| 413 |
+
"grad_norm": 0.09126616269350052,
|
| 414 |
+
"learning_rate": 4.371165644171779e-06,
|
| 415 |
+
"loss": 1.3677804470062256,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.07239263803680981,
|
| 420 |
+
"grad_norm": 0.10076750069856644,
|
| 421 |
+
"learning_rate": 4.447852760736196e-06,
|
| 422 |
+
"loss": 1.517656683921814,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.0736196319018405,
|
| 427 |
+
"grad_norm": 0.09846878796815872,
|
| 428 |
+
"learning_rate": 4.524539877300614e-06,
|
| 429 |
+
"loss": 1.4145147800445557,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.07484662576687116,
|
| 434 |
+
"grad_norm": 0.09265545010566711,
|
| 435 |
+
"learning_rate": 4.601226993865031e-06,
|
| 436 |
+
"loss": 1.3576478958129883,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.07607361963190185,
|
| 441 |
+
"grad_norm": 0.08007940649986267,
|
| 442 |
+
"learning_rate": 4.6779141104294485e-06,
|
| 443 |
+
"loss": 1.2068111896514893,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.07730061349693251,
|
| 448 |
+
"grad_norm": 0.08868364989757538,
|
| 449 |
+
"learning_rate": 4.7546012269938654e-06,
|
| 450 |
+
"loss": 1.6644642353057861,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.0785276073619632,
|
| 455 |
+
"grad_norm": 0.09127894788980484,
|
| 456 |
+
"learning_rate": 4.831288343558282e-06,
|
| 457 |
+
"loss": 1.3978849649429321,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.07975460122699386,
|
| 462 |
+
"grad_norm": 0.08983105421066284,
|
| 463 |
+
"learning_rate": 4.9079754601227e-06,
|
| 464 |
+
"loss": 1.340972661972046,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.08098159509202454,
|
| 469 |
+
"grad_norm": 0.1077636331319809,
|
| 470 |
+
"learning_rate": 4.984662576687116e-06,
|
| 471 |
+
"loss": 1.2714447975158691,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.08220858895705521,
|
| 476 |
+
"grad_norm": 0.08831098675727844,
|
| 477 |
+
"learning_rate": 5.061349693251534e-06,
|
| 478 |
+
"loss": 1.3161592483520508,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.0834355828220859,
|
| 483 |
+
"grad_norm": 0.09379947930574417,
|
| 484 |
+
"learning_rate": 5.138036809815952e-06,
|
| 485 |
+
"loss": 1.4364651441574097,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.08466257668711656,
|
| 490 |
+
"grad_norm": 0.09187101572751999,
|
| 491 |
+
"learning_rate": 5.214723926380368e-06,
|
| 492 |
+
"loss": 1.349583387374878,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.08588957055214724,
|
| 497 |
+
"grad_norm": 0.0946347787976265,
|
| 498 |
+
"learning_rate": 5.2914110429447855e-06,
|
| 499 |
+
"loss": 1.4100244045257568,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.08711656441717791,
|
| 504 |
+
"grad_norm": 0.10264250636100769,
|
| 505 |
+
"learning_rate": 5.368098159509203e-06,
|
| 506 |
+
"loss": 1.3347933292388916,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.08834355828220859,
|
| 511 |
+
"grad_norm": 0.11045140773057938,
|
| 512 |
+
"learning_rate": 5.444785276073619e-06,
|
| 513 |
+
"loss": 1.274242877960205,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.08957055214723926,
|
| 518 |
+
"grad_norm": 0.10263700783252716,
|
| 519 |
+
"learning_rate": 5.521472392638037e-06,
|
| 520 |
+
"loss": 1.4386701583862305,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.09079754601226994,
|
| 525 |
+
"grad_norm": 0.08373517543077469,
|
| 526 |
+
"learning_rate": 5.598159509202455e-06,
|
| 527 |
+
"loss": 1.1995660066604614,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.09202453987730061,
|
| 532 |
+
"grad_norm": 0.09021089226007462,
|
| 533 |
+
"learning_rate": 5.674846625766871e-06,
|
| 534 |
+
"loss": 1.4014225006103516,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.09325153374233129,
|
| 539 |
+
"grad_norm": 0.09492361545562744,
|
| 540 |
+
"learning_rate": 5.751533742331289e-06,
|
| 541 |
+
"loss": 1.2872931957244873,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.09447852760736196,
|
| 546 |
+
"grad_norm": 0.09280592948198318,
|
| 547 |
+
"learning_rate": 5.828220858895706e-06,
|
| 548 |
+
"loss": 1.242187261581421,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.09570552147239264,
|
| 553 |
+
"grad_norm": 0.09655126184225082,
|
| 554 |
+
"learning_rate": 5.9049079754601225e-06,
|
| 555 |
+
"loss": 1.347137451171875,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.09693251533742331,
|
| 560 |
+
"grad_norm": 0.09948047995567322,
|
| 561 |
+
"learning_rate": 5.98159509202454e-06,
|
| 562 |
+
"loss": 1.4971836805343628,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.09815950920245399,
|
| 567 |
+
"grad_norm": 0.10510187596082687,
|
| 568 |
+
"learning_rate": 6.058282208588957e-06,
|
| 569 |
+
"loss": 1.2555480003356934,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.09938650306748466,
|
| 574 |
+
"grad_norm": 0.10650225728750229,
|
| 575 |
+
"learning_rate": 6.134969325153374e-06,
|
| 576 |
+
"loss": 1.4250295162200928,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.10061349693251534,
|
| 581 |
+
"grad_norm": 0.09000247716903687,
|
| 582 |
+
"learning_rate": 6.211656441717792e-06,
|
| 583 |
+
"loss": 1.354022741317749,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.10184049079754601,
|
| 588 |
+
"grad_norm": 0.09123768657445908,
|
| 589 |
+
"learning_rate": 6.288343558282209e-06,
|
| 590 |
+
"loss": 1.3554480075836182,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.10306748466257669,
|
| 595 |
+
"grad_norm": 0.09282216429710388,
|
| 596 |
+
"learning_rate": 6.365030674846626e-06,
|
| 597 |
+
"loss": 1.2707648277282715,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.10429447852760736,
|
| 602 |
+
"grad_norm": 0.09543449431657791,
|
| 603 |
+
"learning_rate": 6.4417177914110434e-06,
|
| 604 |
+
"loss": 1.2168090343475342,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.10552147239263804,
|
| 609 |
+
"grad_norm": 0.09843157976865768,
|
| 610 |
+
"learning_rate": 6.51840490797546e-06,
|
| 611 |
+
"loss": 1.260111927986145,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.1067484662576687,
|
| 616 |
+
"grad_norm": 0.11217689514160156,
|
| 617 |
+
"learning_rate": 6.595092024539877e-06,
|
| 618 |
+
"loss": 1.3698742389678955,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.10797546012269939,
|
| 623 |
+
"grad_norm": 0.09749456495046616,
|
| 624 |
+
"learning_rate": 6.671779141104295e-06,
|
| 625 |
+
"loss": 1.3580715656280518,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.10920245398773006,
|
| 630 |
+
"grad_norm": 0.10477589815855026,
|
| 631 |
+
"learning_rate": 6.748466257668712e-06,
|
| 632 |
+
"loss": 1.3862428665161133,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.11042944785276074,
|
| 637 |
+
"grad_norm": 0.10288488119840622,
|
| 638 |
+
"learning_rate": 6.825153374233129e-06,
|
| 639 |
+
"loss": 1.265109658241272,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.1116564417177914,
|
| 644 |
+
"grad_norm": 0.09684387594461441,
|
| 645 |
+
"learning_rate": 6.901840490797547e-06,
|
| 646 |
+
"loss": 1.323692798614502,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.11288343558282209,
|
| 651 |
+
"grad_norm": 0.10333628952503204,
|
| 652 |
+
"learning_rate": 6.9785276073619635e-06,
|
| 653 |
+
"loss": 1.389283537864685,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.11411042944785275,
|
| 658 |
+
"grad_norm": 0.10879465192556381,
|
| 659 |
+
"learning_rate": 7.05521472392638e-06,
|
| 660 |
+
"loss": 1.395522117614746,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.11533742331288344,
|
| 665 |
+
"grad_norm": 0.09067656099796295,
|
| 666 |
+
"learning_rate": 7.131901840490798e-06,
|
| 667 |
+
"loss": 1.17533540725708,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.1165644171779141,
|
| 672 |
+
"grad_norm": 0.09927186369895935,
|
| 673 |
+
"learning_rate": 7.208588957055215e-06,
|
| 674 |
+
"loss": 1.3598401546478271,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.11779141104294479,
|
| 679 |
+
"grad_norm": 0.1038227528333664,
|
| 680 |
+
"learning_rate": 7.285276073619632e-06,
|
| 681 |
+
"loss": 1.392061471939087,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.11901840490797547,
|
| 686 |
+
"grad_norm": 0.09537981450557709,
|
| 687 |
+
"learning_rate": 7.36196319018405e-06,
|
| 688 |
+
"loss": 1.2397699356079102,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.12024539877300613,
|
| 693 |
+
"grad_norm": 0.08968851715326309,
|
| 694 |
+
"learning_rate": 7.438650306748467e-06,
|
| 695 |
+
"loss": 1.295367956161499,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.12147239263803682,
|
| 700 |
+
"grad_norm": 0.10279387980699539,
|
| 701 |
+
"learning_rate": 7.5153374233128836e-06,
|
| 702 |
+
"loss": 1.2284561395645142,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.12269938650306748,
|
| 707 |
+
"grad_norm": 0.09359531849622726,
|
| 708 |
+
"learning_rate": 7.592024539877301e-06,
|
| 709 |
+
"loss": 1.2822641134262085,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.12392638036809817,
|
| 714 |
+
"grad_norm": 0.07995408773422241,
|
| 715 |
+
"learning_rate": 7.668711656441718e-06,
|
| 716 |
+
"loss": 1.2809827327728271,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.12515337423312883,
|
| 721 |
+
"grad_norm": 0.08832208067178726,
|
| 722 |
+
"learning_rate": 7.745398773006135e-06,
|
| 723 |
+
"loss": 1.3367336988449097,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.1263803680981595,
|
| 728 |
+
"grad_norm": 0.09752494096755981,
|
| 729 |
+
"learning_rate": 7.822085889570554e-06,
|
| 730 |
+
"loss": 1.2547138929367065,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.1276073619631902,
|
| 735 |
+
"grad_norm": 0.0881728082895279,
|
| 736 |
+
"learning_rate": 7.89877300613497e-06,
|
| 737 |
+
"loss": 1.3664880990982056,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.12883435582822086,
|
| 742 |
+
"grad_norm": 0.0837954729795456,
|
| 743 |
+
"learning_rate": 7.975460122699386e-06,
|
| 744 |
+
"loss": 1.217215895652771,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.13006134969325153,
|
| 749 |
+
"grad_norm": 0.09412740916013718,
|
| 750 |
+
"learning_rate": 8.052147239263803e-06,
|
| 751 |
+
"loss": 1.381158709526062,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.1312883435582822,
|
| 756 |
+
"grad_norm": 0.08788621425628662,
|
| 757 |
+
"learning_rate": 8.128834355828221e-06,
|
| 758 |
+
"loss": 1.1602442264556885,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.1325153374233129,
|
| 763 |
+
"grad_norm": 0.07725191116333008,
|
| 764 |
+
"learning_rate": 8.205521472392638e-06,
|
| 765 |
+
"loss": 1.263871669769287,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.13374233128834356,
|
| 770 |
+
"grad_norm": 0.086419977247715,
|
| 771 |
+
"learning_rate": 8.282208588957055e-06,
|
| 772 |
+
"loss": 1.3760960102081299,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.13496932515337423,
|
| 777 |
+
"grad_norm": 0.09353740513324738,
|
| 778 |
+
"learning_rate": 8.358895705521474e-06,
|
| 779 |
+
"loss": 1.3359466791152954,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.1361963190184049,
|
| 784 |
+
"grad_norm": 0.07447539269924164,
|
| 785 |
+
"learning_rate": 8.435582822085889e-06,
|
| 786 |
+
"loss": 1.2698533535003662,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.1374233128834356,
|
| 791 |
+
"grad_norm": 0.10644813627004623,
|
| 792 |
+
"learning_rate": 8.512269938650306e-06,
|
| 793 |
+
"loss": 1.1220934391021729,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.13865030674846626,
|
| 798 |
+
"grad_norm": 0.06901716440916061,
|
| 799 |
+
"learning_rate": 8.588957055214725e-06,
|
| 800 |
+
"loss": 1.1655170917510986,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.13987730061349693,
|
| 805 |
+
"grad_norm": 0.0855763703584671,
|
| 806 |
+
"learning_rate": 8.665644171779141e-06,
|
| 807 |
+
"loss": 1.1486337184906006,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.1411042944785276,
|
| 812 |
+
"grad_norm": 0.09067295491695404,
|
| 813 |
+
"learning_rate": 8.742331288343558e-06,
|
| 814 |
+
"loss": 1.1816922426223755,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.1423312883435583,
|
| 819 |
+
"grad_norm": 0.0844568982720375,
|
| 820 |
+
"learning_rate": 8.819018404907977e-06,
|
| 821 |
+
"loss": 1.215814232826233,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.14355828220858896,
|
| 826 |
+
"grad_norm": 0.06900807470083237,
|
| 827 |
+
"learning_rate": 8.895705521472392e-06,
|
| 828 |
+
"loss": 1.2119998931884766,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.14478527607361963,
|
| 833 |
+
"grad_norm": 0.07901526242494583,
|
| 834 |
+
"learning_rate": 8.972392638036809e-06,
|
| 835 |
+
"loss": 1.2455894947052002,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.1460122699386503,
|
| 840 |
+
"grad_norm": 0.07439431548118591,
|
| 841 |
+
"learning_rate": 9.049079754601228e-06,
|
| 842 |
+
"loss": 1.2518129348754883,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.147239263803681,
|
| 847 |
+
"grad_norm": 0.08350270241498947,
|
| 848 |
+
"learning_rate": 9.125766871165645e-06,
|
| 849 |
+
"loss": 1.2978299856185913,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.14846625766871166,
|
| 854 |
+
"grad_norm": 0.07621041685342789,
|
| 855 |
+
"learning_rate": 9.202453987730062e-06,
|
| 856 |
+
"loss": 1.2295458316802979,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.14969325153374233,
|
| 861 |
+
"grad_norm": 0.08300689607858658,
|
| 862 |
+
"learning_rate": 9.27914110429448e-06,
|
| 863 |
+
"loss": 1.3470526933670044,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.150920245398773,
|
| 868 |
+
"grad_norm": 0.0724540650844574,
|
| 869 |
+
"learning_rate": 9.355828220858897e-06,
|
| 870 |
+
"loss": 1.1989648342132568,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.1521472392638037,
|
| 875 |
+
"grad_norm": 0.07644130289554596,
|
| 876 |
+
"learning_rate": 9.432515337423312e-06,
|
| 877 |
+
"loss": 1.2179319858551025,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.15337423312883436,
|
| 882 |
+
"grad_norm": 0.07522676140069962,
|
| 883 |
+
"learning_rate": 9.509202453987731e-06,
|
| 884 |
+
"loss": 1.2217178344726562,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.15460122699386503,
|
| 889 |
+
"grad_norm": 0.07084149122238159,
|
| 890 |
+
"learning_rate": 9.585889570552148e-06,
|
| 891 |
+
"loss": 1.1610798835754395,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.1558282208588957,
|
| 896 |
+
"grad_norm": 0.07349451631307602,
|
| 897 |
+
"learning_rate": 9.662576687116565e-06,
|
| 898 |
+
"loss": 1.2103276252746582,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.1570552147239264,
|
| 903 |
+
"grad_norm": 0.07179653644561768,
|
| 904 |
+
"learning_rate": 9.739263803680983e-06,
|
| 905 |
+
"loss": 1.247308373451233,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.15828220858895706,
|
| 910 |
+
"grad_norm": 0.0752854123711586,
|
| 911 |
+
"learning_rate": 9.8159509202454e-06,
|
| 912 |
+
"loss": 1.2092695236206055,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.15950920245398773,
|
| 917 |
+
"grad_norm": 0.06951854377985,
|
| 918 |
+
"learning_rate": 9.892638036809815e-06,
|
| 919 |
+
"loss": 1.1004083156585693,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.1607361963190184,
|
| 924 |
+
"grad_norm": 0.07509293407201767,
|
| 925 |
+
"learning_rate": 9.969325153374232e-06,
|
| 926 |
+
"loss": 1.2282463312149048,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.1619631901840491,
|
| 931 |
+
"grad_norm": 0.07161499559879303,
|
| 932 |
+
"learning_rate": 1.0046012269938651e-05,
|
| 933 |
+
"loss": 1.312925100326538,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.16319018404907976,
|
| 938 |
+
"grad_norm": 0.07607123255729675,
|
| 939 |
+
"learning_rate": 1.0122699386503068e-05,
|
| 940 |
+
"loss": 1.3124730587005615,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.16441717791411042,
|
| 945 |
+
"grad_norm": 0.07267063856124878,
|
| 946 |
+
"learning_rate": 1.0199386503067485e-05,
|
| 947 |
+
"loss": 1.1374307870864868,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.1656441717791411,
|
| 952 |
+
"grad_norm": 0.07660125941038132,
|
| 953 |
+
"learning_rate": 1.0276073619631903e-05,
|
| 954 |
+
"loss": 1.1595758199691772,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.1668711656441718,
|
| 959 |
+
"grad_norm": 0.07634468376636505,
|
| 960 |
+
"learning_rate": 1.0352760736196319e-05,
|
| 961 |
+
"loss": 1.1585400104522705,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.16809815950920245,
|
| 966 |
+
"grad_norm": 0.07540547847747803,
|
| 967 |
+
"learning_rate": 1.0429447852760736e-05,
|
| 968 |
+
"loss": 1.2559616565704346,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.16932515337423312,
|
| 973 |
+
"grad_norm": 0.06400100141763687,
|
| 974 |
+
"learning_rate": 1.0506134969325154e-05,
|
| 975 |
+
"loss": 1.2289286851882935,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.1705521472392638,
|
| 980 |
+
"grad_norm": 0.08367716521024704,
|
| 981 |
+
"learning_rate": 1.0582822085889571e-05,
|
| 982 |
+
"loss": 1.169529676437378,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.17177914110429449,
|
| 987 |
+
"grad_norm": 0.07152585685253143,
|
| 988 |
+
"learning_rate": 1.0659509202453988e-05,
|
| 989 |
+
"loss": 1.2492527961730957,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.17300613496932515,
|
| 994 |
+
"grad_norm": 0.07628720253705978,
|
| 995 |
+
"learning_rate": 1.0736196319018407e-05,
|
| 996 |
+
"loss": 1.169081687927246,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.17423312883435582,
|
| 1001 |
+
"grad_norm": 0.07779771089553833,
|
| 1002 |
+
"learning_rate": 1.0812883435582823e-05,
|
| 1003 |
+
"loss": 1.294127106666565,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.1754601226993865,
|
| 1008 |
+
"grad_norm": 0.0831819698214531,
|
| 1009 |
+
"learning_rate": 1.0889570552147239e-05,
|
| 1010 |
+
"loss": 1.191867470741272,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.17668711656441718,
|
| 1015 |
+
"grad_norm": 0.07639773935079575,
|
| 1016 |
+
"learning_rate": 1.0966257668711657e-05,
|
| 1017 |
+
"loss": 1.1590148210525513,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.17791411042944785,
|
| 1022 |
+
"grad_norm": 0.06675959378480911,
|
| 1023 |
+
"learning_rate": 1.1042944785276074e-05,
|
| 1024 |
+
"loss": 1.1139436960220337,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.17914110429447852,
|
| 1029 |
+
"grad_norm": 0.07247823476791382,
|
| 1030 |
+
"learning_rate": 1.1119631901840491e-05,
|
| 1031 |
+
"loss": 1.1570465564727783,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.18036809815950922,
|
| 1036 |
+
"grad_norm": 0.0793304368853569,
|
| 1037 |
+
"learning_rate": 1.119631901840491e-05,
|
| 1038 |
+
"loss": 1.3373682498931885,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.18159509202453988,
|
| 1043 |
+
"grad_norm": 0.08718875050544739,
|
| 1044 |
+
"learning_rate": 1.1273006134969327e-05,
|
| 1045 |
+
"loss": 1.1467812061309814,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.18282208588957055,
|
| 1050 |
+
"grad_norm": 0.07898775488138199,
|
| 1051 |
+
"learning_rate": 1.1349693251533742e-05,
|
| 1052 |
+
"loss": 1.1690555810928345,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.18404907975460122,
|
| 1057 |
+
"grad_norm": 0.0748438760638237,
|
| 1058 |
+
"learning_rate": 1.142638036809816e-05,
|
| 1059 |
+
"loss": 1.286328673362732,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.18527607361963191,
|
| 1064 |
+
"grad_norm": 0.07474487274885178,
|
| 1065 |
+
"learning_rate": 1.1503067484662577e-05,
|
| 1066 |
+
"loss": 1.2229455709457397,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.18650306748466258,
|
| 1071 |
+
"grad_norm": 0.07763181626796722,
|
| 1072 |
+
"learning_rate": 1.1579754601226994e-05,
|
| 1073 |
+
"loss": 1.131850242614746,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.18773006134969325,
|
| 1078 |
+
"grad_norm": 0.07221898436546326,
|
| 1079 |
+
"learning_rate": 1.1656441717791411e-05,
|
| 1080 |
+
"loss": 1.1305968761444092,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.18895705521472392,
|
| 1085 |
+
"grad_norm": 0.07231416553258896,
|
| 1086 |
+
"learning_rate": 1.173312883435583e-05,
|
| 1087 |
+
"loss": 1.2581983804702759,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.1901840490797546,
|
| 1092 |
+
"grad_norm": 0.0842069461941719,
|
| 1093 |
+
"learning_rate": 1.1809815950920245e-05,
|
| 1094 |
+
"loss": 1.1937918663024902,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.19141104294478528,
|
| 1099 |
+
"grad_norm": 0.07470091432332993,
|
| 1100 |
+
"learning_rate": 1.1886503067484662e-05,
|
| 1101 |
+
"loss": 1.1321823596954346,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.19263803680981595,
|
| 1106 |
+
"grad_norm": 0.07048668712377548,
|
| 1107 |
+
"learning_rate": 1.196319018404908e-05,
|
| 1108 |
+
"loss": 1.186060905456543,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.19386503067484662,
|
| 1113 |
+
"grad_norm": 0.15513236820697784,
|
| 1114 |
+
"learning_rate": 1.2039877300613497e-05,
|
| 1115 |
+
"loss": 1.1082484722137451,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.1950920245398773,
|
| 1120 |
+
"grad_norm": 0.07174337655305862,
|
| 1121 |
+
"learning_rate": 1.2116564417177914e-05,
|
| 1122 |
+
"loss": 1.0334205627441406,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.19631901840490798,
|
| 1127 |
+
"grad_norm": 0.08637174218893051,
|
| 1128 |
+
"learning_rate": 1.2193251533742333e-05,
|
| 1129 |
+
"loss": 1.2800869941711426,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.19754601226993865,
|
| 1134 |
+
"grad_norm": 0.07679158449172974,
|
| 1135 |
+
"learning_rate": 1.2269938650306748e-05,
|
| 1136 |
+
"loss": 1.0969552993774414,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.19877300613496932,
|
| 1141 |
+
"grad_norm": 0.07408922910690308,
|
| 1142 |
+
"learning_rate": 1.2346625766871165e-05,
|
| 1143 |
+
"loss": 1.0420407056808472,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.2,
|
| 1148 |
+
"grad_norm": 0.07723739743232727,
|
| 1149 |
+
"learning_rate": 1.2423312883435584e-05,
|
| 1150 |
+
"loss": 1.2170075178146362,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.20122699386503068,
|
| 1155 |
+
"grad_norm": 0.09736181795597076,
|
| 1156 |
+
"learning_rate": 1.25e-05,
|
| 1157 |
+
"loss": 1.092185139656067,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.20245398773006135,
|
| 1162 |
+
"grad_norm": 0.08557657897472382,
|
| 1163 |
+
"learning_rate": 1.2576687116564418e-05,
|
| 1164 |
+
"loss": 1.1464152336120605,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.20368098159509201,
|
| 1169 |
+
"grad_norm": 0.08090342581272125,
|
| 1170 |
+
"learning_rate": 1.2653374233128834e-05,
|
| 1171 |
+
"loss": 1.0590012073516846,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.2049079754601227,
|
| 1176 |
+
"grad_norm": 0.0782066136598587,
|
| 1177 |
+
"learning_rate": 1.2730061349693251e-05,
|
| 1178 |
+
"loss": 1.093062162399292,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.20613496932515338,
|
| 1183 |
+
"grad_norm": 0.07601075619459152,
|
| 1184 |
+
"learning_rate": 1.280674846625767e-05,
|
| 1185 |
+
"loss": 1.0593127012252808,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.20736196319018405,
|
| 1190 |
+
"grad_norm": 0.07887541502714157,
|
| 1191 |
+
"learning_rate": 1.2883435582822087e-05,
|
| 1192 |
+
"loss": 1.1101746559143066,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.2085889570552147,
|
| 1197 |
+
"grad_norm": 0.08362209796905518,
|
| 1198 |
+
"learning_rate": 1.2960122699386504e-05,
|
| 1199 |
+
"loss": 1.127945065498352,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.2098159509202454,
|
| 1204 |
+
"grad_norm": 0.07187578082084656,
|
| 1205 |
+
"learning_rate": 1.303680981595092e-05,
|
| 1206 |
+
"loss": 0.9966148138046265,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.21104294478527608,
|
| 1211 |
+
"grad_norm": 0.08967337757349014,
|
| 1212 |
+
"learning_rate": 1.3113496932515338e-05,
|
| 1213 |
+
"loss": 1.2105052471160889,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.21226993865030674,
|
| 1218 |
+
"grad_norm": 0.08062509447336197,
|
| 1219 |
+
"learning_rate": 1.3190184049079754e-05,
|
| 1220 |
+
"loss": 1.124169111251831,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.2134969325153374,
|
| 1225 |
+
"grad_norm": 0.08591330051422119,
|
| 1226 |
+
"learning_rate": 1.3266871165644173e-05,
|
| 1227 |
+
"loss": 1.2784122228622437,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.2147239263803681,
|
| 1232 |
+
"grad_norm": 0.07611163705587387,
|
| 1233 |
+
"learning_rate": 1.334355828220859e-05,
|
| 1234 |
+
"loss": 1.3006565570831299,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.21595092024539878,
|
| 1239 |
+
"grad_norm": 0.09474623948335648,
|
| 1240 |
+
"learning_rate": 1.3420245398773007e-05,
|
| 1241 |
+
"loss": 1.0671237707138062,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.21717791411042944,
|
| 1246 |
+
"grad_norm": 0.08161427825689316,
|
| 1247 |
+
"learning_rate": 1.3496932515337424e-05,
|
| 1248 |
+
"loss": 1.1499321460723877,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.2184049079754601,
|
| 1253 |
+
"grad_norm": 0.0793696790933609,
|
| 1254 |
+
"learning_rate": 1.357361963190184e-05,
|
| 1255 |
+
"loss": 1.1806647777557373,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.2196319018404908,
|
| 1260 |
+
"grad_norm": 0.07412323355674744,
|
| 1261 |
+
"learning_rate": 1.3650306748466258e-05,
|
| 1262 |
+
"loss": 1.1109105348587036,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.22085889570552147,
|
| 1267 |
+
"grad_norm": 0.09603255242109299,
|
| 1268 |
+
"learning_rate": 1.3726993865030676e-05,
|
| 1269 |
+
"loss": 1.0471618175506592,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.22208588957055214,
|
| 1274 |
+
"grad_norm": 0.08905616402626038,
|
| 1275 |
+
"learning_rate": 1.3803680981595093e-05,
|
| 1276 |
+
"loss": 1.1427825689315796,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.2233128834355828,
|
| 1281 |
+
"grad_norm": 0.09254536777734756,
|
| 1282 |
+
"learning_rate": 1.388036809815951e-05,
|
| 1283 |
+
"loss": 1.1951453685760498,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.2245398773006135,
|
| 1288 |
+
"grad_norm": 0.08542929589748383,
|
| 1289 |
+
"learning_rate": 1.3957055214723927e-05,
|
| 1290 |
+
"loss": 1.1082501411437988,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.22576687116564417,
|
| 1295 |
+
"grad_norm": 0.08667684346437454,
|
| 1296 |
+
"learning_rate": 1.4033742331288344e-05,
|
| 1297 |
+
"loss": 1.172175645828247,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.22699386503067484,
|
| 1302 |
+
"grad_norm": 0.08812960237264633,
|
| 1303 |
+
"learning_rate": 1.411042944785276e-05,
|
| 1304 |
+
"loss": 1.113857626914978,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.2282208588957055,
|
| 1309 |
+
"grad_norm": 0.08759750425815582,
|
| 1310 |
+
"learning_rate": 1.418711656441718e-05,
|
| 1311 |
+
"loss": 1.0720980167388916,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.2294478527607362,
|
| 1316 |
+
"grad_norm": 0.07663634419441223,
|
| 1317 |
+
"learning_rate": 1.4263803680981596e-05,
|
| 1318 |
+
"loss": 1.1362175941467285,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.23067484662576687,
|
| 1323 |
+
"grad_norm": 0.0884539932012558,
|
| 1324 |
+
"learning_rate": 1.4340490797546013e-05,
|
| 1325 |
+
"loss": 1.030583381652832,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.23190184049079754,
|
| 1330 |
+
"grad_norm": 0.07207372039556503,
|
| 1331 |
+
"learning_rate": 1.441717791411043e-05,
|
| 1332 |
+
"loss": 1.1791778802871704,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.2331288343558282,
|
| 1337 |
+
"grad_norm": 0.09309247136116028,
|
| 1338 |
+
"learning_rate": 1.4493865030674847e-05,
|
| 1339 |
+
"loss": 1.1558406352996826,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.2343558282208589,
|
| 1344 |
+
"grad_norm": 0.08264083415269852,
|
| 1345 |
+
"learning_rate": 1.4570552147239264e-05,
|
| 1346 |
+
"loss": 1.1436799764633179,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.23558282208588957,
|
| 1351 |
+
"grad_norm": 0.08998411893844604,
|
| 1352 |
+
"learning_rate": 1.4647239263803681e-05,
|
| 1353 |
+
"loss": 0.9984644055366516,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.23680981595092024,
|
| 1358 |
+
"grad_norm": 0.09304746985435486,
|
| 1359 |
+
"learning_rate": 1.47239263803681e-05,
|
| 1360 |
+
"loss": 1.1322174072265625,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.23803680981595093,
|
| 1365 |
+
"grad_norm": 0.09598280489444733,
|
| 1366 |
+
"learning_rate": 1.4800613496932516e-05,
|
| 1367 |
+
"loss": 1.103399634361267,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.2392638036809816,
|
| 1372 |
+
"grad_norm": 0.09808170050382614,
|
| 1373 |
+
"learning_rate": 1.4877300613496933e-05,
|
| 1374 |
+
"loss": 1.1747708320617676,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.24049079754601227,
|
| 1379 |
+
"grad_norm": 0.08757835626602173,
|
| 1380 |
+
"learning_rate": 1.495398773006135e-05,
|
| 1381 |
+
"loss": 1.135438323020935,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.24171779141104294,
|
| 1386 |
+
"grad_norm": 0.08952710032463074,
|
| 1387 |
+
"learning_rate": 1.5030674846625767e-05,
|
| 1388 |
+
"loss": 1.0426082611083984,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.24294478527607363,
|
| 1393 |
+
"grad_norm": 0.09966392815113068,
|
| 1394 |
+
"learning_rate": 1.5107361963190184e-05,
|
| 1395 |
+
"loss": 1.2231348752975464,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.2441717791411043,
|
| 1400 |
+
"grad_norm": 0.08228705823421478,
|
| 1401 |
+
"learning_rate": 1.5184049079754603e-05,
|
| 1402 |
+
"loss": 1.0428478717803955,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.24539877300613497,
|
| 1407 |
+
"grad_norm": 0.09374398738145828,
|
| 1408 |
+
"learning_rate": 1.526073619631902e-05,
|
| 1409 |
+
"loss": 1.057676076889038,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.24662576687116564,
|
| 1414 |
+
"grad_norm": 0.08426011353731155,
|
| 1415 |
+
"learning_rate": 1.5337423312883436e-05,
|
| 1416 |
+
"loss": 1.1756813526153564,
|
| 1417 |
+
"step": 201
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.24785276073619633,
|
| 1421 |
+
"grad_norm": 0.08629194647073746,
|
| 1422 |
+
"learning_rate": 1.5414110429447852e-05,
|
| 1423 |
+
"loss": 1.1612563133239746,
|
| 1424 |
+
"step": 202
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.249079754601227,
|
| 1428 |
+
"grad_norm": 0.1029244139790535,
|
| 1429 |
+
"learning_rate": 1.549079754601227e-05,
|
| 1430 |
+
"loss": 1.0064386129379272,
|
| 1431 |
+
"step": 203
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.25030674846625767,
|
| 1435 |
+
"grad_norm": 0.08551669865846634,
|
| 1436 |
+
"learning_rate": 1.5567484662576686e-05,
|
| 1437 |
+
"loss": 1.2138303518295288,
|
| 1438 |
+
"step": 204
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.25153374233128833,
|
| 1442 |
+
"grad_norm": 0.08521132916212082,
|
| 1443 |
+
"learning_rate": 1.5644171779141108e-05,
|
| 1444 |
+
"loss": 1.0655517578125,
|
| 1445 |
+
"step": 205
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.252760736196319,
|
| 1449 |
+
"grad_norm": 0.0902361199259758,
|
| 1450 |
+
"learning_rate": 1.5720858895705523e-05,
|
| 1451 |
+
"loss": 1.1724493503570557,
|
| 1452 |
+
"step": 206
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.25398773006134967,
|
| 1456 |
+
"grad_norm": 0.0905335545539856,
|
| 1457 |
+
"learning_rate": 1.579754601226994e-05,
|
| 1458 |
+
"loss": 1.0633145570755005,
|
| 1459 |
+
"step": 207
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.2552147239263804,
|
| 1463 |
+
"grad_norm": 0.10272892564535141,
|
| 1464 |
+
"learning_rate": 1.5874233128834357e-05,
|
| 1465 |
+
"loss": 1.034580111503601,
|
| 1466 |
+
"step": 208
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.25644171779141106,
|
| 1470 |
+
"grad_norm": 0.08878074586391449,
|
| 1471 |
+
"learning_rate": 1.5950920245398772e-05,
|
| 1472 |
+
"loss": 1.1094441413879395,
|
| 1473 |
+
"step": 209
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.25766871165644173,
|
| 1477 |
+
"grad_norm": 0.09403765946626663,
|
| 1478 |
+
"learning_rate": 1.602760736196319e-05,
|
| 1479 |
+
"loss": 1.0656667947769165,
|
| 1480 |
+
"step": 210
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.2588957055214724,
|
| 1484 |
+
"grad_norm": 0.10467862337827682,
|
| 1485 |
+
"learning_rate": 1.6104294478527606e-05,
|
| 1486 |
+
"loss": 1.1456003189086914,
|
| 1487 |
+
"step": 211
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.26012269938650306,
|
| 1491 |
+
"grad_norm": 0.09688597917556763,
|
| 1492 |
+
"learning_rate": 1.6180981595092028e-05,
|
| 1493 |
+
"loss": 1.124730110168457,
|
| 1494 |
+
"step": 212
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.26134969325153373,
|
| 1498 |
+
"grad_norm": 0.09323239326477051,
|
| 1499 |
+
"learning_rate": 1.6257668711656443e-05,
|
| 1500 |
+
"loss": 1.1329385042190552,
|
| 1501 |
+
"step": 213
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.2625766871165644,
|
| 1505 |
+
"grad_norm": 0.10989087074995041,
|
| 1506 |
+
"learning_rate": 1.633435582822086e-05,
|
| 1507 |
+
"loss": 1.2534266710281372,
|
| 1508 |
+
"step": 214
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.26380368098159507,
|
| 1512 |
+
"grad_norm": 0.10287831723690033,
|
| 1513 |
+
"learning_rate": 1.6411042944785277e-05,
|
| 1514 |
+
"loss": 1.0936100482940674,
|
| 1515 |
+
"step": 215
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.2650306748466258,
|
| 1519 |
+
"grad_norm": 0.09896902740001678,
|
| 1520 |
+
"learning_rate": 1.6487730061349692e-05,
|
| 1521 |
+
"loss": 1.0307230949401855,
|
| 1522 |
+
"step": 216
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.26625766871165646,
|
| 1526 |
+
"grad_norm": 0.10131006687879562,
|
| 1527 |
+
"learning_rate": 1.656441717791411e-05,
|
| 1528 |
+
"loss": 1.1618880033493042,
|
| 1529 |
+
"step": 217
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.2674846625766871,
|
| 1533 |
+
"grad_norm": 0.10399206727743149,
|
| 1534 |
+
"learning_rate": 1.664110429447853e-05,
|
| 1535 |
+
"loss": 1.1229549646377563,
|
| 1536 |
+
"step": 218
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.2687116564417178,
|
| 1540 |
+
"grad_norm": 0.10053529590368271,
|
| 1541 |
+
"learning_rate": 1.6717791411042948e-05,
|
| 1542 |
+
"loss": 1.1616917848587036,
|
| 1543 |
+
"step": 219
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.26993865030674846,
|
| 1547 |
+
"grad_norm": 0.09529908001422882,
|
| 1548 |
+
"learning_rate": 1.6794478527607363e-05,
|
| 1549 |
+
"loss": 1.0340030193328857,
|
| 1550 |
+
"step": 220
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.27116564417177913,
|
| 1554 |
+
"grad_norm": 0.1017000749707222,
|
| 1555 |
+
"learning_rate": 1.6871165644171778e-05,
|
| 1556 |
+
"loss": 1.0947508811950684,
|
| 1557 |
+
"step": 221
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.2723926380368098,
|
| 1561 |
+
"grad_norm": 0.08638525754213333,
|
| 1562 |
+
"learning_rate": 1.6947852760736197e-05,
|
| 1563 |
+
"loss": 0.9798234701156616,
|
| 1564 |
+
"step": 222
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.27361963190184047,
|
| 1568 |
+
"grad_norm": 0.10133469104766846,
|
| 1569 |
+
"learning_rate": 1.7024539877300612e-05,
|
| 1570 |
+
"loss": 1.0582237243652344,
|
| 1571 |
+
"step": 223
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.2748466257668712,
|
| 1575 |
+
"grad_norm": 0.10113056749105453,
|
| 1576 |
+
"learning_rate": 1.7101226993865034e-05,
|
| 1577 |
+
"loss": 1.066800832748413,
|
| 1578 |
+
"step": 224
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.27607361963190186,
|
| 1582 |
+
"grad_norm": 0.11324694007635117,
|
| 1583 |
+
"learning_rate": 1.717791411042945e-05,
|
| 1584 |
+
"loss": 1.1267540454864502,
|
| 1585 |
+
"step": 225
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.2773006134969325,
|
| 1589 |
+
"grad_norm": 0.0964084267616272,
|
| 1590 |
+
"learning_rate": 1.7254601226993868e-05,
|
| 1591 |
+
"loss": 1.0880162715911865,
|
| 1592 |
+
"step": 226
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.2785276073619632,
|
| 1596 |
+
"grad_norm": 0.10354617238044739,
|
| 1597 |
+
"learning_rate": 1.7331288343558283e-05,
|
| 1598 |
+
"loss": 1.150836706161499,
|
| 1599 |
+
"step": 227
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.27975460122699386,
|
| 1603 |
+
"grad_norm": 0.10236093401908875,
|
| 1604 |
+
"learning_rate": 1.7407975460122698e-05,
|
| 1605 |
+
"loss": 0.9434213042259216,
|
| 1606 |
+
"step": 228
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.2809815950920245,
|
| 1610 |
+
"grad_norm": 0.09847301989793777,
|
| 1611 |
+
"learning_rate": 1.7484662576687117e-05,
|
| 1612 |
+
"loss": 1.0203105211257935,
|
| 1613 |
+
"step": 229
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.2822085889570552,
|
| 1617 |
+
"grad_norm": 0.1049259603023529,
|
| 1618 |
+
"learning_rate": 1.7561349693251535e-05,
|
| 1619 |
+
"loss": 1.0045392513275146,
|
| 1620 |
+
"step": 230
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.28343558282208586,
|
| 1624 |
+
"grad_norm": 0.09362269192934036,
|
| 1625 |
+
"learning_rate": 1.7638036809815954e-05,
|
| 1626 |
+
"loss": 0.9903603196144104,
|
| 1627 |
+
"step": 231
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.2846625766871166,
|
| 1631 |
+
"grad_norm": 0.08344310522079468,
|
| 1632 |
+
"learning_rate": 1.771472392638037e-05,
|
| 1633 |
+
"loss": 1.078027367591858,
|
| 1634 |
+
"step": 232
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.28588957055214725,
|
| 1638 |
+
"grad_norm": 0.14989130198955536,
|
| 1639 |
+
"learning_rate": 1.7791411042944784e-05,
|
| 1640 |
+
"loss": 0.8905891180038452,
|
| 1641 |
+
"step": 233
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.2871165644171779,
|
| 1645 |
+
"grad_norm": 0.11933330446481705,
|
| 1646 |
+
"learning_rate": 1.7868098159509203e-05,
|
| 1647 |
+
"loss": 1.0191709995269775,
|
| 1648 |
+
"step": 234
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.2883435582822086,
|
| 1652 |
+
"grad_norm": 0.09907590597867966,
|
| 1653 |
+
"learning_rate": 1.7944785276073618e-05,
|
| 1654 |
+
"loss": 0.97510826587677,
|
| 1655 |
+
"step": 235
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.28957055214723926,
|
| 1659 |
+
"grad_norm": 0.11432763934135437,
|
| 1660 |
+
"learning_rate": 1.8021472392638037e-05,
|
| 1661 |
+
"loss": 1.2066056728363037,
|
| 1662 |
+
"step": 236
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.2907975460122699,
|
| 1666 |
+
"grad_norm": 0.09880590438842773,
|
| 1667 |
+
"learning_rate": 1.8098159509202455e-05,
|
| 1668 |
+
"loss": 1.0608339309692383,
|
| 1669 |
+
"step": 237
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.2920245398773006,
|
| 1673 |
+
"grad_norm": 0.09431140124797821,
|
| 1674 |
+
"learning_rate": 1.8174846625766874e-05,
|
| 1675 |
+
"loss": 0.994207501411438,
|
| 1676 |
+
"step": 238
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.29325153374233126,
|
| 1680 |
+
"grad_norm": 0.11933495849370956,
|
| 1681 |
+
"learning_rate": 1.825153374233129e-05,
|
| 1682 |
+
"loss": 0.9558770656585693,
|
| 1683 |
+
"step": 239
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.294478527607362,
|
| 1687 |
+
"grad_norm": 0.11472880095243454,
|
| 1688 |
+
"learning_rate": 1.8328220858895704e-05,
|
| 1689 |
+
"loss": 1.0349183082580566,
|
| 1690 |
+
"step": 240
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.29570552147239265,
|
| 1694 |
+
"grad_norm": 0.09867944568395615,
|
| 1695 |
+
"learning_rate": 1.8404907975460123e-05,
|
| 1696 |
+
"loss": 1.0970228910446167,
|
| 1697 |
+
"step": 241
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.2969325153374233,
|
| 1701 |
+
"grad_norm": 0.10022281855344772,
|
| 1702 |
+
"learning_rate": 1.848159509202454e-05,
|
| 1703 |
+
"loss": 1.093743920326233,
|
| 1704 |
+
"step": 242
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.298159509202454,
|
| 1708 |
+
"grad_norm": 0.12287919968366623,
|
| 1709 |
+
"learning_rate": 1.855828220858896e-05,
|
| 1710 |
+
"loss": 1.1307411193847656,
|
| 1711 |
+
"step": 243
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.29938650306748466,
|
| 1715 |
+
"grad_norm": 0.09696297347545624,
|
| 1716 |
+
"learning_rate": 1.8634969325153376e-05,
|
| 1717 |
+
"loss": 1.1624317169189453,
|
| 1718 |
+
"step": 244
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.3006134969325153,
|
| 1722 |
+
"grad_norm": 0.11268558353185654,
|
| 1723 |
+
"learning_rate": 1.8711656441717794e-05,
|
| 1724 |
+
"loss": 1.1427913904190063,
|
| 1725 |
+
"step": 245
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.301840490797546,
|
| 1729 |
+
"grad_norm": 0.09550510346889496,
|
| 1730 |
+
"learning_rate": 1.878834355828221e-05,
|
| 1731 |
+
"loss": 1.0877418518066406,
|
| 1732 |
+
"step": 246
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.3030674846625767,
|
| 1736 |
+
"grad_norm": 0.09527410566806793,
|
| 1737 |
+
"learning_rate": 1.8865030674846625e-05,
|
| 1738 |
+
"loss": 1.0739914178848267,
|
| 1739 |
+
"step": 247
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.3042944785276074,
|
| 1743 |
+
"grad_norm": 0.14008916914463043,
|
| 1744 |
+
"learning_rate": 1.8941717791411043e-05,
|
| 1745 |
+
"loss": 0.9480798244476318,
|
| 1746 |
+
"step": 248
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.30552147239263805,
|
| 1750 |
+
"grad_norm": 0.1293039619922638,
|
| 1751 |
+
"learning_rate": 1.9018404907975462e-05,
|
| 1752 |
+
"loss": 0.992428183555603,
|
| 1753 |
+
"step": 249
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.3067484662576687,
|
| 1757 |
+
"grad_norm": 0.11473323404788971,
|
| 1758 |
+
"learning_rate": 1.909509202453988e-05,
|
| 1759 |
+
"loss": 1.0926830768585205,
|
| 1760 |
+
"step": 250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.3079754601226994,
|
| 1764 |
+
"grad_norm": 0.09950664639472961,
|
| 1765 |
+
"learning_rate": 1.9171779141104296e-05,
|
| 1766 |
+
"loss": 1.2386255264282227,
|
| 1767 |
+
"step": 251
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.30920245398773005,
|
| 1771 |
+
"grad_norm": 0.10663459450006485,
|
| 1772 |
+
"learning_rate": 1.924846625766871e-05,
|
| 1773 |
+
"loss": 1.137174129486084,
|
| 1774 |
+
"step": 252
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.3104294478527607,
|
| 1778 |
+
"grad_norm": 0.12015614658594131,
|
| 1779 |
+
"learning_rate": 1.932515337423313e-05,
|
| 1780 |
+
"loss": 1.018200397491455,
|
| 1781 |
+
"step": 253
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.3116564417177914,
|
| 1785 |
+
"grad_norm": 0.12178294360637665,
|
| 1786 |
+
"learning_rate": 1.9401840490797545e-05,
|
| 1787 |
+
"loss": 1.03646981716156,
|
| 1788 |
+
"step": 254
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.3128834355828221,
|
| 1792 |
+
"grad_norm": 0.09648360311985016,
|
| 1793 |
+
"learning_rate": 1.9478527607361967e-05,
|
| 1794 |
+
"loss": 1.1479485034942627,
|
| 1795 |
+
"step": 255
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.3141104294478528,
|
| 1799 |
+
"grad_norm": 0.10974877327680588,
|
| 1800 |
+
"learning_rate": 1.9555214723926382e-05,
|
| 1801 |
+
"loss": 1.1105828285217285,
|
| 1802 |
+
"step": 256
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.31533742331288345,
|
| 1806 |
+
"grad_norm": 0.13123326003551483,
|
| 1807 |
+
"learning_rate": 1.96319018404908e-05,
|
| 1808 |
+
"loss": 1.0254418849945068,
|
| 1809 |
+
"step": 257
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.3165644171779141,
|
| 1813 |
+
"grad_norm": 0.12058497965335846,
|
| 1814 |
+
"learning_rate": 1.9708588957055216e-05,
|
| 1815 |
+
"loss": 0.8520700335502625,
|
| 1816 |
+
"step": 258
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.3177914110429448,
|
| 1820 |
+
"grad_norm": 0.10527869313955307,
|
| 1821 |
+
"learning_rate": 1.978527607361963e-05,
|
| 1822 |
+
"loss": 1.057407021522522,
|
| 1823 |
+
"step": 259
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.31901840490797545,
|
| 1827 |
+
"grad_norm": 0.12831807136535645,
|
| 1828 |
+
"learning_rate": 1.986196319018405e-05,
|
| 1829 |
+
"loss": 0.9605754017829895,
|
| 1830 |
+
"step": 260
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.3202453987730061,
|
| 1834 |
+
"grad_norm": 0.10611746460199356,
|
| 1835 |
+
"learning_rate": 1.9938650306748465e-05,
|
| 1836 |
+
"loss": 1.121097445487976,
|
| 1837 |
+
"step": 261
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.3214723926380368,
|
| 1841 |
+
"grad_norm": 0.10287187248468399,
|
| 1842 |
+
"learning_rate": 2.0015337423312887e-05,
|
| 1843 |
+
"loss": 1.0894691944122314,
|
| 1844 |
+
"step": 262
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.3226993865030675,
|
| 1848 |
+
"grad_norm": 0.11541418731212616,
|
| 1849 |
+
"learning_rate": 2.0092024539877302e-05,
|
| 1850 |
+
"loss": 0.9634550213813782,
|
| 1851 |
+
"step": 263
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.3239263803680982,
|
| 1855 |
+
"grad_norm": 0.13788478076457977,
|
| 1856 |
+
"learning_rate": 2.016871165644172e-05,
|
| 1857 |
+
"loss": 1.0188679695129395,
|
| 1858 |
+
"step": 264
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.32515337423312884,
|
| 1862 |
+
"grad_norm": 0.12389227002859116,
|
| 1863 |
+
"learning_rate": 2.0245398773006136e-05,
|
| 1864 |
+
"loss": 1.0685219764709473,
|
| 1865 |
+
"step": 265
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.3263803680981595,
|
| 1869 |
+
"grad_norm": 0.1358790248632431,
|
| 1870 |
+
"learning_rate": 2.032208588957055e-05,
|
| 1871 |
+
"loss": 0.9753469228744507,
|
| 1872 |
+
"step": 266
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.3276073619631902,
|
| 1876 |
+
"grad_norm": 0.1116497740149498,
|
| 1877 |
+
"learning_rate": 2.039877300613497e-05,
|
| 1878 |
+
"loss": 0.957251787185669,
|
| 1879 |
+
"step": 267
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.32883435582822085,
|
| 1883 |
+
"grad_norm": 0.11138273775577545,
|
| 1884 |
+
"learning_rate": 2.0475460122699388e-05,
|
| 1885 |
+
"loss": 0.9344768524169922,
|
| 1886 |
+
"step": 268
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.3300613496932515,
|
| 1890 |
+
"grad_norm": 0.1283080279827118,
|
| 1891 |
+
"learning_rate": 2.0552147239263807e-05,
|
| 1892 |
+
"loss": 1.0072486400604248,
|
| 1893 |
+
"step": 269
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.3312883435582822,
|
| 1897 |
+
"grad_norm": 0.1293177753686905,
|
| 1898 |
+
"learning_rate": 2.0628834355828222e-05,
|
| 1899 |
+
"loss": 0.9404339790344238,
|
| 1900 |
+
"step": 270
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.3325153374233129,
|
| 1904 |
+
"grad_norm": 0.10337118804454803,
|
| 1905 |
+
"learning_rate": 2.0705521472392637e-05,
|
| 1906 |
+
"loss": 0.9937950372695923,
|
| 1907 |
+
"step": 271
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.3337423312883436,
|
| 1911 |
+
"grad_norm": 0.10898245871067047,
|
| 1912 |
+
"learning_rate": 2.0782208588957056e-05,
|
| 1913 |
+
"loss": 1.1300337314605713,
|
| 1914 |
+
"step": 272
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.33496932515337424,
|
| 1918 |
+
"grad_norm": 0.1548905074596405,
|
| 1919 |
+
"learning_rate": 2.085889570552147e-05,
|
| 1920 |
+
"loss": 0.9663505554199219,
|
| 1921 |
+
"step": 273
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.3361963190184049,
|
| 1925 |
+
"grad_norm": 0.12634064257144928,
|
| 1926 |
+
"learning_rate": 2.0935582822085893e-05,
|
| 1927 |
+
"loss": 0.8915446400642395,
|
| 1928 |
+
"step": 274
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.3374233128834356,
|
| 1932 |
+
"grad_norm": 0.09657935798168182,
|
| 1933 |
+
"learning_rate": 2.1012269938650308e-05,
|
| 1934 |
+
"loss": 0.9893382787704468,
|
| 1935 |
+
"step": 275
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.33865030674846625,
|
| 1939 |
+
"grad_norm": 0.17486917972564697,
|
| 1940 |
+
"learning_rate": 2.1088957055214727e-05,
|
| 1941 |
+
"loss": 1.070754051208496,
|
| 1942 |
+
"step": 276
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.3398773006134969,
|
| 1946 |
+
"grad_norm": 0.14501982927322388,
|
| 1947 |
+
"learning_rate": 2.1165644171779142e-05,
|
| 1948 |
+
"loss": 1.1186362504959106,
|
| 1949 |
+
"step": 277
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.3411042944785276,
|
| 1953 |
+
"grad_norm": 0.13628800213336945,
|
| 1954 |
+
"learning_rate": 2.1242331288343557e-05,
|
| 1955 |
+
"loss": 0.9450318217277527,
|
| 1956 |
+
"step": 278
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.3423312883435583,
|
| 1960 |
+
"grad_norm": 0.11076204478740692,
|
| 1961 |
+
"learning_rate": 2.1319018404907976e-05,
|
| 1962 |
+
"loss": 1.005497932434082,
|
| 1963 |
+
"step": 279
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.34355828220858897,
|
| 1967 |
+
"grad_norm": 0.13485747575759888,
|
| 1968 |
+
"learning_rate": 2.1395705521472395e-05,
|
| 1969 |
+
"loss": 0.895561933517456,
|
| 1970 |
+
"step": 280
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.34478527607361964,
|
| 1974 |
+
"grad_norm": 0.12088459730148315,
|
| 1975 |
+
"learning_rate": 2.1472392638036813e-05,
|
| 1976 |
+
"loss": 1.3100700378417969,
|
| 1977 |
+
"step": 281
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.3460122699386503,
|
| 1981 |
+
"grad_norm": 0.11534463614225388,
|
| 1982 |
+
"learning_rate": 2.154907975460123e-05,
|
| 1983 |
+
"loss": 1.11163330078125,
|
| 1984 |
+
"step": 282
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.347239263803681,
|
| 1988 |
+
"grad_norm": 0.12682971358299255,
|
| 1989 |
+
"learning_rate": 2.1625766871165647e-05,
|
| 1990 |
+
"loss": 1.022303581237793,
|
| 1991 |
+
"step": 283
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.34846625766871164,
|
| 1995 |
+
"grad_norm": 0.1394464671611786,
|
| 1996 |
+
"learning_rate": 2.1702453987730062e-05,
|
| 1997 |
+
"loss": 1.1607928276062012,
|
| 1998 |
+
"step": 284
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.3496932515337423,
|
| 2002 |
+
"grad_norm": 0.12041673809289932,
|
| 2003 |
+
"learning_rate": 2.1779141104294477e-05,
|
| 2004 |
+
"loss": 0.9233322739601135,
|
| 2005 |
+
"step": 285
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.350920245398773,
|
| 2009 |
+
"grad_norm": 0.14270088076591492,
|
| 2010 |
+
"learning_rate": 2.1855828220858896e-05,
|
| 2011 |
+
"loss": 1.100630760192871,
|
| 2012 |
+
"step": 286
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.3521472392638037,
|
| 2016 |
+
"grad_norm": 0.147483691573143,
|
| 2017 |
+
"learning_rate": 2.1932515337423315e-05,
|
| 2018 |
+
"loss": 1.0364069938659668,
|
| 2019 |
+
"step": 287
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.35337423312883437,
|
| 2023 |
+
"grad_norm": 0.11873972415924072,
|
| 2024 |
+
"learning_rate": 2.2009202453987733e-05,
|
| 2025 |
+
"loss": 1.0084702968597412,
|
| 2026 |
+
"step": 288
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.35460122699386504,
|
| 2030 |
+
"grad_norm": 0.1410827338695526,
|
| 2031 |
+
"learning_rate": 2.208588957055215e-05,
|
| 2032 |
+
"loss": 0.9259920120239258,
|
| 2033 |
+
"step": 289
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.3558282208588957,
|
| 2037 |
+
"grad_norm": 0.12482478469610214,
|
| 2038 |
+
"learning_rate": 2.2162576687116564e-05,
|
| 2039 |
+
"loss": 0.8635483384132385,
|
| 2040 |
+
"step": 290
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.3570552147239264,
|
| 2044 |
+
"grad_norm": 0.11416301131248474,
|
| 2045 |
+
"learning_rate": 2.2239263803680982e-05,
|
| 2046 |
+
"loss": 1.1208245754241943,
|
| 2047 |
+
"step": 291
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.35828220858895704,
|
| 2051 |
+
"grad_norm": 0.14102044701576233,
|
| 2052 |
+
"learning_rate": 2.2315950920245397e-05,
|
| 2053 |
+
"loss": 1.0029829740524292,
|
| 2054 |
+
"step": 292
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.3595092024539877,
|
| 2058 |
+
"grad_norm": 0.25360825657844543,
|
| 2059 |
+
"learning_rate": 2.239263803680982e-05,
|
| 2060 |
+
"loss": 1.0258023738861084,
|
| 2061 |
+
"step": 293
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.36073619631901843,
|
| 2065 |
+
"grad_norm": 0.13373959064483643,
|
| 2066 |
+
"learning_rate": 2.2469325153374235e-05,
|
| 2067 |
+
"loss": 1.0896992683410645,
|
| 2068 |
+
"step": 294
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.3619631901840491,
|
| 2072 |
+
"grad_norm": 0.13520075380802155,
|
| 2073 |
+
"learning_rate": 2.2546012269938653e-05,
|
| 2074 |
+
"loss": 1.1489715576171875,
|
| 2075 |
+
"step": 295
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.36319018404907977,
|
| 2079 |
+
"grad_norm": 0.11745908111333847,
|
| 2080 |
+
"learning_rate": 2.262269938650307e-05,
|
| 2081 |
+
"loss": 1.0147686004638672,
|
| 2082 |
+
"step": 296
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.36441717791411044,
|
| 2086 |
+
"grad_norm": 0.12096819281578064,
|
| 2087 |
+
"learning_rate": 2.2699386503067484e-05,
|
| 2088 |
+
"loss": 1.2157928943634033,
|
| 2089 |
+
"step": 297
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.3656441717791411,
|
| 2093 |
+
"grad_norm": 0.12824957072734833,
|
| 2094 |
+
"learning_rate": 2.2776073619631902e-05,
|
| 2095 |
+
"loss": 1.037453532218933,
|
| 2096 |
+
"step": 298
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.36687116564417177,
|
| 2100 |
+
"grad_norm": 0.13326457142829895,
|
| 2101 |
+
"learning_rate": 2.285276073619632e-05,
|
| 2102 |
+
"loss": 0.9710744023323059,
|
| 2103 |
+
"step": 299
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.36809815950920244,
|
| 2107 |
+
"grad_norm": 0.14364396035671234,
|
| 2108 |
+
"learning_rate": 2.292944785276074e-05,
|
| 2109 |
+
"loss": 0.9510235786437988,
|
| 2110 |
+
"step": 300
|
| 2111 |
+
}
|
| 2112 |
+
],
|
| 2113 |
+
"logging_steps": 1,
|
| 2114 |
+
"max_steps": 16300,
|
| 2115 |
+
"num_input_tokens_seen": 0,
|
| 2116 |
+
"num_train_epochs": 20,
|
| 2117 |
+
"save_steps": 300,
|
| 2118 |
+
"stateful_callbacks": {
|
| 2119 |
+
"TrainerControl": {
|
| 2120 |
+
"args": {
|
| 2121 |
+
"should_epoch_stop": false,
|
| 2122 |
+
"should_evaluate": false,
|
| 2123 |
+
"should_log": false,
|
| 2124 |
+
"should_save": true,
|
| 2125 |
+
"should_training_stop": false
|
| 2126 |
+
},
|
| 2127 |
+
"attributes": {}
|
| 2128 |
+
}
|
| 2129 |
+
},
|
| 2130 |
+
"total_flos": 8.39372739969024e+17,
|
| 2131 |
+
"train_batch_size": 8,
|
| 2132 |
+
"trial_name": null,
|
| 2133 |
+
"trial_params": null
|
| 2134 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d2da33ebc281d72d4c5e6bb5df446b43b8ebfb23b62285abd0b16424914d26f
|
| 3 |
+
size 5841
|